Risk Mirror
AI Security, Without the Hallucinations
What it does
It sits between your users and your LLM (OpenAI/Anthropic) and strips out sensitive data before it leaves your server. The Tech (Zero AI Inference): Instead of asking an LLM "is this safe?", I use: 152 PII Types: My custom engine covers everything from US Social Security Numbers to Indian Aadhaar cards and HIPAA identifiers. Shannon Entropy: To detect high-entropy strings (API keys, passwords) that regex misses. Deterministic Rules: 100% consistency. No "maybe."
Does the same job
all alternatives →
- AFA free AI risk assessment tool for LLM applications2025 · gettavo.com · ▲37
We’ve built an AI risk assessment tool designed specifically for GenAI/LLM applications. It's still early, but we’d love your feedback. Here’s what it does: 1. it performs comprehensive AI risk assessments by analyzing your codebase against different AI regulation/framework or even internal policies. It identifies potential issues and suggests fixes directly through one click PRs. 2. the first framework the platform supports is OWASP Top 10 for LLM Applications 2025, upcoming framework will be ISO 42001 as well as custom policy documents. 3. we're a small, early stage team, so the…
- PDPII Detective, Leveraging LLMs for Cost-Effective PII Detection2024 · github.com · ▲6
PII Detective is a web application designed to identify, classify, and protect Personally Identifiable Information (PII) in data platforms such as BigQuery and Snowflake. It leverages LLMs to identify PII column names, and with human-in-the-loop validation, uses Dynamic Data Masking Policies to easily enforce Access Control Limits (ACLs) while minimizing user friction. For comparison, GCP has a "Sensitive Data Protection" service which promises similar functionality, but it can become extremely costly since it runs hundreds of regex queries on the entire contents of the table. For…
- OSOpen-Source tool for automatic MCP API on top of your database for LLMs2025 · github.com · ▲5
We’re building an open-source tool that makes it easy to expose secure, LLM-optimized APIs on top of your structured data—without manually designing endpoints or worrying about compliance. AI agents and LLM-powered applications need structured access to data, but traditional APIs and databases weren’t built with AI workloads in mind. Our tool automatically generates APIs that: - Filter out PII & sensitive data to comply with GDPR, CPRA, SOC 2, and other regulations. - Provide traceability & auditing, so AI apps aren’t black boxes, and security teams stay in control. - Optimize for AI…
- CLCompliant LLM toolkit for ensuring compliance & security of AI systems2025 · github.com · ▲7
With the right technique, I was able to break the so-called secure models like Claude and OpenAI. So, I built an open-source tool to automate this and find security holes in any hosted model. I got claude-sonnet-4 to demonstrate the following harmful behavior: - steal data from downstream tool calls using sql injection, code injection and template injection attacks - install spyware or malware using prompt obfuscation to send data to a third-party server Try it yourself with this simple command: pip install compliant-llm && compliant-llm dashboard
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
